中文
相关论文

相关论文: Seeing Voices: Generating A-Roll Video from Audio …

200 篇论文

The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). However, these paradigms have inherent limitations. (1) Images…

Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2023-09-04 Linsen Song , Wayne Wu , Chaoyou Fu , Chen Change Loy , Ran He

Binaural audio provides a listener with 3D sound sensation, allowing a rich perceptual experience of the scene. However, binaural recordings are scarcely available and require nontrivial expertise and equipment to obtain. We propose to…

计算机视觉与模式识别 · 计算机科学 2019-04-10 Ruohan Gao , Kristen Grauman

We introduce the visual acoustic matching task, in which an audio clip is transformed to sound like it was recorded in a target environment. Given an image of the target environment and a waveform for the source audio, the goal is to…

计算机视觉与模式识别 · 计算机科学 2022-06-15 Changan Chen , Ruohan Gao , Paul Calamia , Kristen Grauman

Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained control over the generated audio, especially in terms of…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Bingliang Li , Fengyu Yang , Yuxin Mao , Qingwen Ye , Hongkai Chen , Yiran Zhong

Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…

声音 · 计算机科学 2024-09-17 Mingjing Yi , Ming Li

Advances in technology have led to the development of methods that can create desired visual multimedia. In particular, image generation using deep learning has been extensively studied across diverse fields. In comparison, video…

计算机视觉与模式识别 · 计算机科学 2021-06-29 Doyeon Kim , Donggyu Joo , Junmo Kim

Recent text-to-video diffusion models can generate compelling video sequences, yet they remain silent -- missing the semantic, emotional, and atmospheric cues that audio provides. We introduce LTX-2, an open-source foundational model…

In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements…

计算机视觉与模式识别 · 计算机科学 2024-05-27 Shiqi Yang , Zhi Zhong , Mengjie Zhao , Shusuke Takahashi , Masato Ishii , Takashi Shibuya , Yuki Mitsufuji

We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos…

多媒体 · 计算机科学 2024-09-12 Yan-Bo Lin , Yu Tian , Linjie Yang , Gedas Bertasius , Heng Wang

Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios…

多媒体 · 计算机科学 2025-04-11 Xiaohao Liu , Teng Tu , Yunshan Ma , Tat-Seng Chua

Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative…

多媒体 · 计算机科学 2025-10-03 Chetwin Low , Weimin Wang , Calder Katyal

Although humans have the innate ability to imagine multiple possible actions from videos, it remains an extraordinary challenge for computers due to the intricate camera movements and montages. Most existing motion generation methods…

计算机视觉与模式识别 · 计算机科学 2024-08-14 Liangdong Qiu , Chengxing Yu , Yanran Li , Zhao Wang , Haibin Huang , Chongyang Ma , Di Zhang , Pengfei Wan , Xiaoguang Han

In this paper, we introduce a novel audio-visual multi-modal bridging framework that can utilize both audio and visual information, even with uni-modal inputs. We exploit a memory network that stores source (i.e., visual) and target (i.e.,…

计算机视觉与模式识别 · 计算机科学 2022-04-05 Minsu Kim , Joanna Hong , Se Jin Park , Yong Man Ro

Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…

计算机视觉与模式识别 · 计算机科学 2025-06-23 Zeyuan Yang , Xueyang Yu , Delin Chen , Maohao Shen , Chuang Gan

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Ye Tian , Ling Yang , Haotian Yang , Yuan Gao , Yufan Deng , Jingmin Chen , Xintao Wang , Zhaochen Yu , Xin Tao , Pengfei Wan , Di Zhang , Bin Cui

Retrieval-Augmented Generation (RAG) has demonstrated remarkable success in enhancing Large Language Models (LLMs) through external knowledge integration, yet its application has primarily focused on textual content, leaving the rich domain…

信息检索 · 计算机科学 2025-02-04 Xubin Ren , Lingrui Xu , Long Xia , Shuaiqiang Wang , Dawei Yin , Chao Huang

A Music Video (MV) is a video aiming at visually illustrating or extending the meaning of its background music. This paper proposes a novel method to automatically generate, from an input music track, a music video made of segments of…

多媒体 · 计算机科学 2019-05-30 Sarah Gross , Xingxing Wei , Jun Zhu

We present SONIQUE, a model for generating background music tailored to video content. Unlike traditional video-to-music generation approaches, which rely heavily on paired audio-visual datasets, SONIQUE leverages unpaired data, combining…

声音 · 计算机科学 2025-02-27 Liqian Zhang , Magdalena Fuentes

We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip. It is a challenging task to gener-ate the…

计算机视觉与模式识别 · 计算机科学 2020-11-06 Hao Zhu , Yi Li , Feixia Zhu , Aihua Zheng , Ran He